© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110723
    Prev
    Next
    INDEX
    Explanations

    xml, programming, and lists

    np_acts-logits-general · gemini-2.5-flash-lite

    non-Latin script characters, particularly from Asian and other writing systems.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    -2.86
    ה
    -2.83
    0
    -2.69
    
    -2.64
     digitais
    -2.45
     sabun
    -2.44
    Ꮏ
    -2.39
     spesifik
    -2.33
     colorida
    -2.30
    Ꮽ
    -2.30
    POSITIVE LOGITS
     they
    3.31
    ’
    2.94
    筇
    2.86
     falsche
    2.83
     usual
    2.59
    揍
    2.58
     pertinent
    2.52
    偏偏
    2.52
     zupełnie
    2.52
     ensuing
    2.50
    Activations Density 0.001%

    No Known Activations